让大模型生成更可控：用滑块等界面直接调节文本风格
From Words to Widgets for Controllable LLM Generation
- 将自然语言提示转为可操作的图形控件，如滑块、下拉框
- 用户通过调节控件能更精准达成想要的语气和风格
- 可视化反馈帮助理解每项设置对输出的影响，适合非技术用户
自然语言仍是用户与大语言模型交互的主要方式，但人们在通过提示词精确表达主观偏好（如语调、风格、强调）时常感困难。本文提出「可塑提示」（Malleable Prompting），一种新的交互式提示技术，将自然语言中的偏好表达转化为图形化控件（如滑块、下拉框、开关），用户可直接配置这些控件来引导生成结果，并通过可视化展示每个控制项对输出的影响，支持属性溯源与多轮对比。为此，我们引入一种基于偏好表达及其控件值动态调节生成过程中词元概率分布的解码算法。用户研究显示，相比仅使用自然语言提示，该方法显著提升了用户实现目标偏好的准确性，且被评价为更具可控性和透明度。
原文摘要 · Abstract (English)
Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceived as more controllable and transparent than natural language prompting alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。